{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/citebart-learning-to-generate-citations-for","title":"CiteBART: Learning to Generate Citations for Local Citation Recommendation","arxiv_id":"2412.17534","date":"2024-12-23","proceeding":null,"authors":["Ege Yiğit Çelik","Selma Tekir"],"abstract":"Local citation recommendation (LCR) suggests a set of papers for a citation placeholder within a given context. The task has evolved as generative approaches have become more promising than the traditional pre-fetch and re-rank-based state-of-the-art approaches. This paper introduces citation-specific pre-training within an encoder-decoder architecture, where author-date citation tokens are masked to learn to reconstruct them to fulfill LCR. There are two variants for this pre-training. In the local context-only base scheme (CiteBART-Base), the citation token in a local context is masked to learn to predict the citation. The global version (CiteBART-Global) extends the local context with the citing paper's title and abstract to enrich the learning signal. CiteBART-Global achieves state-of-the-art performance on LCR benchmarks except for the FullTextPeerRead dataset, which is quite small to see the advantage of generative pre-training. The effect is significant in the larger benchmarks, e.g., Refseer and ArXiv., with the Refseer benchmark-trained model emerging as the best-performing model. We perform comprehensive experiments, including an ablation study, a qualitative analysis, and a taxonomy of hallucinations with detailed statistics. Our analyses confirm that CiteBART-Global has a cross-dataset generalization capability; the macro hallucination rate (MaHR) at the top-3 predictions is 4\\%, and when the ground-truth is in the top-k prediction list, the hallucination tendency in the other predictions drops significantly.","url_abs":"https://arxiv.org/abs/2412.17534v2","url_pdf":"https://arxiv.org/pdf/2412.17534v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"citebart-learning-to-generate-citations-for","repo_url":"https://github.com/eyclk/citationrecommendation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"citation-prediction","task_name":"Citation Prediction"},{"task_slug":"citation-recommendation","task_name":"Citation Recommendation"},{"task_slug":"citation-worthiness","task_name":"Citation worthiness"},{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2412.17534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.17534"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eyclk/citationrecommendation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":16},"by_repo_kind":{"official":{"samples":16,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ed93e4ca62fbffb6","entry":"add_spaces_after_commas","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"train/train_base_cit_pred_BART.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/train/train_base_cit_pred_BART.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed93e4ca62fbffb6"}},{"code_sha256_prefix":"7b67f2595aec1eb4","entry":"assign_appropriate_year_for_null_years","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_arxiv_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_arxiv_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b67f2595aec1eb4"}},{"code_sha256_prefix":"8ea3a7ab27e61dc5","entry":"assign_appropriate_year_for_null_years","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_refseer_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_refseer_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ea3a7ab27e61dc5"}},{"code_sha256_prefix":"38ebfde953f7ced5","entry":"calculate_average_and_median_of_cit_per_ref","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"utils/data_statistic_utils.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/utils/data_statistic_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38ebfde953f7ced5"}},{"code_sha256_prefix":"88ebca421726370f","entry":"check_if_raw_text_has_special_tags","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_refseer_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_refseer_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88ebca421726370f"}},{"code_sha256_prefix":"4f99c48215b33468","entry":"check_if_string_contains_year","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_acl200_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_acl200_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f99c48215b33468"}},{"code_sha256_prefix":"5700d07b9aac33af","entry":"create_appearance_count_frequency_dict","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"utils/data_statistic_utils.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/utils/data_statistic_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5700d07b9aac33af"}},{"code_sha256_prefix":"a4cbaa0a0a646c3b","entry":"create_target_token_for_ref_paper_id","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_acl200_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_acl200_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4cbaa0a0a646c3b"}},{"code_sha256_prefix":"9b3d0dd4083197b1","entry":"create_target_token_for_ref_paper_id","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_arxiv_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_arxiv_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b3d0dd4083197b1"}},{"code_sha256_prefix":"523150d2455c7d31","entry":"create_target_token_for_ref_paper_id","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_peerread_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_peerread_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"523150d2455c7d31"}},{"code_sha256_prefix":"10449f995043c586","entry":"create_target_token_for_ref_paper_id","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_refseer_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_refseer_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10449f995043c586"}},{"code_sha256_prefix":"85c6162dc111a623","entry":"fill_mask","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"train/train_base_cit_pred_BART.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/train/train_base_cit_pred_BART.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85c6162dc111a623"}},{"code_sha256_prefix":"ebd620899935776d","entry":"find_all_appearance_counts","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"utils/data_statistic_utils.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/utils/data_statistic_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ebd620899935776d"}},{"code_sha256_prefix":"27f10f8117094aa8","entry":"place_mask_and_target_cit_on_ground_truth_context","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"preprocessing/base_datasets/data_preprocess_for_acl200_base.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/preprocessing/base_datasets/data_preprocess_for_acl200_base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27f10f8117094aa8"}},{"code_sha256_prefix":"4f57ec01008c6bae","entry":"preprocess_function","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"train/train_base_cit_pred_BART.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/train/train_base_cit_pred_BART.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f57ec01008c6bae"}},{"code_sha256_prefix":"0e7c221cf16af4e4","entry":"preprocess_function","repo":"eyclk/citationrecommendation","repo_kind":"official","path":"train/train_global_cit_pred_BART.py","file_url":"https://github.com/eyclk/citationrecommendation/blob/HEAD/train/train_global_cit_pred_BART.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e7c221cf16af4e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}